© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93530
    Prev
    Next
    INDEX
    Explanations

    word fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ostante
    -0.60
     entry
    -0.51
    مصادر
    -0.51
     autorytatywna
    -0.51
    Diwedd
    -0.51
    tanleria
    -0.49
     ISTAT
    -0.48
     SV
    -0.48
     ranks
    -0.48
     tra
    -0.48
    POSITIVE LOGITS
    a
    0.72
    s
    0.65
    e
    0.63
    i
    0.60
    ی
    0.56
    ebe
    0.54
    %";
    0.52
    ske
    0.52
    iation
    0.52
    tling
    0.51
    Activations Density 0.029%

    No Known Activations